Machine Learning
Enhancing Activation Energy Prediction under Data Constraints Using Graph Neural Networks
We developed a Graph Neural Network (GNN) framework leveraging low-cost computational data to predict activation energy with high accuracy. The delta learning method significantly reduced error (MAE: 3.85 kcal/mol) while requiring only 20–30% of high-level data. This approach offers a scalable, efficient solution for modeling activation energies in diverse chemical systems.
Advancing vapoer pressure prediction: A machine learning approach with directed message passing neural networks
Our lab developed a machine-learning model using Directed Message Passing Neural Networks (D-MPNNs) to predict vapor pressure with high accuracy (AARD 0.617 vs. 1.36 for traditional methods). The model relies only on molecular structures and temperature data, eliminating the need for experimental inputs. This work showcases machine learning's potential to transform chemical property prediction.
Machine learning-guided strategies for reaction conditions design and optimization
This study explores the use of machine learning (ML) for optimizing chemical reactions, showcasing its potential to enhance prediction accuracy and efficiency. By combining ML with high-throughput experimentation, the research improves reaction conditions and yields, surpassing traditional methods. The integration of ML with automated platforms paves the way for self-driving laboratories and novel reaction discovery.
Unveiling the Role of Quantum Mechanical Descriptors in Machine Learning for Chemical Property Prediction
Our latest research explores how quantum mechanical (QM) descriptors enhance deep graph neural networks (GNNs) for predicting chemical properties like solubility, toxicity, and reactivity. We find that QM descriptors significantly improve GNN performance in data-limited scenarios, boosting accuracy and generalizability.
AutoTemplate—Revolutionizing Chemical Reaction Datasets for Machine Learning Applications in Organic Chemistry
We introduce AutoTemplate, an innovative data preprocessing protocol that enhances the quality of chemical reaction datasets for machine learning applications in organic chemistry. This research addresses critical challenges in data quality, leading to improved accuracy and usability for tasks like yield prediction, retrosynthesis, and reaction condition prediction. Our findings significantly advance the reliability of machine learning models in the field.
Advanced Deep Learning Model Enhances Chemical Synthesis Planning
This research introduces a novel two-stage deep neural network that accurately predicts optimal reaction conditions for chemical synthesis. By utilizing advanced machine learning techniques, it streamlines the process of chemical reactions, enhancing efficiency. This approach has the potential to save time and resources in laboratories globally.
Integrating Chemical Information into Reinforcement Learning for Molecular Geometry Optimization
This study presents a two-stage deep neural network that predicts optimal reaction conditions for chemical synthesis. By applying advanced machine learning techniques, it enhances the efficiency of chemical reactions. The approach aims to save time and resources in laboratories globally.
Machine Learning in Chemical Kinetics and Thermochemistry
This chapter explores recent advancements in applying machine learning to predict molecular thermochemical and kinetic properties. It highlights the significant impact of these techniques on understanding chemical reactions and optimizing reaction systems. The research showcases the potential of machine learning to enhance insights in the field of molecular sciences.
Advancing Climate Change Research with Machine Learning Models for Greenhouse Gas Prediction
This research develops machine learning models to accurately predict the radiative efficiency of greenhouse gases, which are crucial for understanding global warming. The models are trained on a comprehensive dataset generated from density functional theory and infrared spectra calculations. This approach enables efficient predictions for a wide range of halogenated and non-halogenated greenhouse gases, aiding informed decision-making in climate change mitigation.
New Approach to Explainable Uncertainty Quantification in Molecular Property Prediction
This research presents a novel method for quantifying uncertainties in deep learning models used for predicting molecular properties. It enhances transparency and explainability, allowing for the identification of factors contributing to uncertainty. This advancement improves the reliability of machine learning models in chemical research.
Quantum Mechanics
Simulation-Driven Insights into the Role of Ammonium-Amine Additives in Perovskite Solar Cells
Our research investigates how ammonium- and amine-based additives differently affect the efficiency and stability of inverted perovskite solar cells (PVSCs). Using density functional theory (DFT) simulations, we reveal why phenethylamine (PEA) outperforms phenethylammonium iodide (PEA+) in enhancing PVSC performance and durability.
Advanced Copper-Based Electrocatalysts for Efficient Nitrate Reduction to Ammonia
Our research explores how different support materials enhance the efficiency and selectivity of copper-based electrocatalysts for converting nitrate to ammonia. By developing and studying copper catalysts supported by ceria/carbon, zirconia/carbon, and pure carbon, we identified key factors that influence catalytic performance.
Innovative Catalytic System for Reductive Amination of Furfural and Furfurylamine
Our collaborative research introduces an efficient catalytic system for producing difurfurylamine (DiFAM), a chemical used in pharmaceuticals and polymers. We developed a novel methoxide and MIL-53-NH2(Al)-derived Ru catalyst, significantly improving the production process. Using density functional theory (DFT), we explored the reaction mechanism, providing deeper insights into its efficiency.
Enhanced QM/MM Simulations for Accurate Modeling of Adsorption and Catalysis in Zr-Based MOFs
Our research advances hybrid quantum mechanics/molecular mechanics (QM/MM) simulations for accurately modeling adsorption and catalytic reactions in zirconium-based metal-organic frameworks (Zr-MOFs). These materials are crucial for gas storage, separation, and catalysis.
Biomass-Derived Furan Oligomers Show Promise for Next-Generation Electrochromic Devices
Our research introduces a novel electrochromic material made from biomass, offering sustainable solutions for smart windows and energy-efficient displays. The study focuses on a trifuran oligomer, synthesized via a one-pot reaction, which shows excellent color-changing properties, transitioning from light yellow to red with high efficiency. Advanced computational methods, including density functional theory (DFT), were used to reveal the molecular mechanisms driving these electrochromic behaviors.
Machine Learning and DFT Unlock New Insights into Cerium Oxide Catalysts
Our research introduces a deep learning approach combined with infrared (IR) spectroscopy and density functional theory (DFT) to analyze the surface properties of cerium oxide (CeO2) catalysts. By using IR spectra, we developed a model that quickly predicts CeO2 surface structures, offering a faster and more efficient method than traditional techniques. This work provides valuable insights for optimizing catalyst design and performance in environmental and redox reactions.
Fast Water Transport Mechanism Unveiled in UTSA-280 Metal-Organic Framework
Our research uncovers a novel water transport mechanism in the UTSA-280 metal-organic framework (MOF), featuring a unique knock-off mechanism that allows incoming water molecules to displace coordinated ones for efficient mass transfer. This pseudo-three-dimensional transport has important implications for membrane-based separation technologies, especially in water purification and ethanol separation.
Mixed-Linker Strategy Improves Structural Stability of Metal-Organic Framework Membranes for Gas Separation
Our study employed computational optimization to introduce a mixed-linker strategy that enhances the structural stability of CAU-10-based metal-organic framework (MOF) membranes. By replacing pyridine-3,5-dicarboxylate (PDC) with benzene-1,3-dicarboxylate (BDC), we significantly improved membrane performance. This approach effectively addresses the structural flexibility issue, making MOF membranes more suitable for industrial CO2/CH4 separations.
Automating Reaction Kinetics with Arkane – A New Tool for Chemical Kinetics and Thermochemistry
This project is about Arkane, an open-source tool that automates complex chemical kinetic and thermodynamic calculations. The software streamlines critical processes essential for understanding chemical reactions. Developed by an international team, Arkane enhances the efficiency and accessibility of computational analysis in the field.
This research explores an innovative method for converting biomass-derived furfural (FAL) into tetrahydrofurfuryl alcohol (THFA) using Ni-supported catalysts with sodium borohydride (NaBH4) as a hydrogen source. The computational analysis highlights the efficiency and cost-effectiveness of this approach, making it a promising alternative for producing THFA.